halfmoon-mind/rubric-evaluator
Evaluate Claude Code and Codex skill directories with deterministic rubric checks and graded, fixable reports.
Evaluate Claude Code and Codex skill directories with deterministic rubric checks and graded, fixable reports.
npx add-skill halfmoon-mind/rubric-evaluatorEvaluate Claude Code and Codex skill directories with deterministic rubric checks and graded, fixable reports.
Claude Code skill: bridge to OpenAI Codex CLI with seven operation modes (plan-review, verify, ask, insight, delegate, batch-ask, batch-delegate).
Tiny Context7 alternative for Claude Code, OpenAI Codex CLI, and Cursor IDE. Cross-agent SKILL.md + POSIX helper + cache directory. No MCP, no daemon, no SQLite, no embeddings.
A personal collection of [Agent Skills](https://agentskills.io/) — reusable instruction sets that give AI agents domain-specific expertise.
stuff i made for myself, some of it orignally quite situational, but now generalized for reuse
AI coding agent configuration for Claude Code and GitHub Copilot — shared CLAUDE.md, rules, hooks, and skills
Multi-source cross-validated memory MCP server for AI agents (Rust, jieba CJK, local-first, AGPL)